© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 2644
    Prev
    Next
    INDEX
    Explanations

    the word "fruit" and words that often accompany it such as "vegetables" and "juice"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rams
    -0.59
    ndra
    -0.58
     Nadel
    -0.57
    érieurs
    -0.56
    GLAS
    -0.55
     Holocene
    -0.55
    zawa
    -0.55
     secoli
    -0.54
     web
    -0.53
     Enfield
    -0.53
    POSITIVE LOGITS
     fruit
    3.00
     fruits
    2.81
     Fruit
    2.78
    fruit
    2.70
    Fruit
    2.66
     FRUIT
    2.58
     Fruits
    2.56
    fruits
    2.38
    Fruits
    2.33
     Früchte
    1.89
    Activations Density 0.028%

    No Known Activations